Agent skill

Interspeech Writing Style

by brycewang-stanford in brycewang-stanford/Awesome-Journal-Skills

A skill your agent uses when writing or compressing an INTERSPEECH paper into its 4 content pages — the abstract-and-index-terms opening, task-first framing for a mixed science/engineering…

MITAuto-check passedWriting & Content

Install Interspeech Writing Style

skills CLI
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill interspeech-writing-style -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install brycewang-stanford/Awesome-Journal-Skills interspeech-writing-style --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/INTERSPEECH-Skills/skills/interspeech-writing-style .claude/skills/interspeech-writing-style && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
interspeech-writing-style
GitHub stars
1.2k
Token cost
~1.6k tokens
SKILL.md length
723 words
Files
1
Skills in repo
2,387
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when writing or compressing an INTERSPEECH paper into its 4 content pages — the abstract-and-index-terms opening, task-first framing for a mixed science/engineering…

  • Works in 5 steps: Cut motivation prose — Interspeech… → Convert method paragraphs to diffs… → Merge tables; move per-condition detail… → …
  • Compressing an INTERSPEECH paper into its 4 content pages — the abstract-and-index-terms opening
  • SKILL.md covers The opening contract, Density moves that buy space…, Speech-community diction and The compression order (when…, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Interspeech Writing Style is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when writing or compressing an INTERSPEECH paper into its 4 content pages — the abstract-and-index-terms opening, task-first framing for a mixed science/engineering readership, table and figure economy, protocol one-liners that preserve rigor under compression, and the cuts that shrink pages without shrinking claims.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Writing & Content, covering Brand voice and tone. The repository describes itself as: Journal-specific Claude Code/Codex skill packs covering mainstream journals — AER, QJE, Nature, Cell, 管理世界, 经济研究 & 200+ more — your fast track to getting published. | 覆盖主流期刊的… The licence is MIT.

When your agent uses it

  • Compressing an INTERSPEECH paper into its 4 content pages — the abstract-and-index-terms opening
  • Task-first framing for a mixed science/engineering readership
  • Table and figure economy
  • Protocol one-liners that preserve rigor under compression

Example prompts

  • “/interspeech-writing-style”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Cut motivation prose — Interspeech readers arrive pre-motivated.
  2. Convert method paragraphs to diffs against cited standards.
  3. Merge tables; move per-condition detail into a results sentence.
  4. Trim the intro's third rehearsal of the contribution.
  5. Only then consider dropping an experiment — and if the paper still does not

What it can do on your machine

Read from SKILL.md and the folder at commit 932eb23. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Interspeech Writing Style loads about 1.6k tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 723 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~87
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from brycewang-stanford/Awesome-Journal-Skills at commit 932eb23, republished under its MIT licence (© brycewang-stanford). 723 words, ~1,607 tokens.

Download SKILL.mdSave it as .claude/skills/interspeech-writing-style/SKILL.md (or your agent's skills folder).
name
interspeech-writing-style
description
Use when writing or compressing an INTERSPEECH paper into its 4 content pages — the abstract-and-index-terms opening, task-first framing for a mixed science/engineering readership, table and figure economy, protocol one-liners that preserve rigor under compression, and the cuts that shrink pages without shrinking claims.

INTERSPEECH Writing Style

Four pages is not a short paper; it is a different literary form. The Interspeech house style evolved to let a reader — who may be a phonetician, an ASR engineer, or an area chair skimming forty PDFs — extract task, method, corpus, metric, and delta in one pass. Everything below serves that one-pass property.

The opening contract

  • Title: task and mechanism, in community vocabulary. Searchable in the ISCA Archive beats clever.
  • Abstract (~100–150 words): task → limitation of current practice → your move → corpus + metric + headline number → one-clause takeaway. Numbers belong in Interspeech abstracts; "significant improvements" without a number reads as evasion.
  • Index Terms: the paper kit's index-terms line is your search surface — pick the 3–5 terms your intended reviewers actually use.
  • Introduction (~0.75 column): no history of deep learning. Name the task in sentence one, the gap by sentence three, the contribution list by the end.

Density moves that buy space honestly

MoveBeforeAfter
Protocol one-linerA paragraph on data prep"We follow the ESPnet LibriSpeech recipe (commit X) except: …"
Diff-based method descriptionRe-derive the known architecture"As in Conformer [n], with two changes: …"
Table consolidationSeparate tables per test setOne table, sets as column groups, best in bold
Citation compressionThree sentences of related work per itemClause-level positioning: "unlike streaming approaches [4,5], we…"
Figure economyArchitecture diagram redrawing the standardOne figure that carries the finding (error breakdown, trade-off curve)

The related-work section can shrink to a paragraph if positioning is woven into the introduction — common and accepted at this venue (see interspeech-related-work).

Speech-community diction

  • Report metrics with their conditions attached: "WER 4.8% on test-other (no LM)", "EER 0.92% on Vox1-O", "MOS 4.1 ± 0.08". A bare number is a red flag.
  • Use canonical corpus/partition names; do not rename "dev-clean" to "validation".
  • Past tense for what you did, present for what the system does, no "novel" as a self-description — the reviewer decides novelty.
  • Acronyms: expand once, then commit. An Interspeech paper drowning in undefined acronyms fails the one-pass property for the scientist half of the audience.
  • Claims scale with evidence verbs: "improves" needs a CI; "suggests" tolerates a trend; "solves" needs more than four pages of anything.

The compression order (when you are at 5.5 pages)

  1. Cut motivation prose — Interspeech readers arrive pre-motivated.
  2. Convert method paragraphs to diffs against cited standards.
  3. Merge tables; move per-condition detail into a results sentence.
  4. Trim the intro's third rehearsal of the contribution.
  5. Only then consider dropping an experiment — and if the paper still does not fit, that is a Long Paper or journal signal, not a formatting problem.

Never buy space with template tricks; the PDF checker and the format police are real (see interspeech-submission).

Show full SKILL.md (273 more words)Show less

Micro-example: results sentence, before → after

text
Before (3 lines):  We evaluate our proposed method on the LibriSpeech
dataset. Our method achieves significant improvements over the baseline.
Results are shown in Table 2, which demonstrates the effectiveness.

After (2 lines):  On LibriSpeech, the proposed front end reduces WER from
5.6% to 4.9% on test-other (Table 2; paired bootstrap p<0.01), with the
largest gains on utterances under 3 s.

The after-version is shorter and carries corpus, metric, delta, significance, and an analysis hook.

A working section budget for 4 pages

SectionBudgetJob
Abstract + index terms0.15 coltask→move→corpus→metric→delta
1. Introduction0.75 colgap, hypothesis, contribution — no history lesson
2. Relation to prior work0.3–0.5 colclause-level positioning (may merge into 1)
3. Method1.2 colthe diff against cited standards, one figure max
4. Experimental setup0.6 colcorpus, protocol one-liners, disclosure block
5. Results + analysis1.5 coldecisive table, ablation, one error-pattern finding
6. Conclusions0.2 colfinding restated, scoped future sentence

Budgets flex ±30% by paper type (science papers grow §4–5, systems papers §3), but a draft violating the total by a full column will not compress overnight.

Bilingual/global audience note

Interspeech's readership is the most linguistically diverse of the major ML-adjacent venues. Prefer plain constructions, keep sentences under ~25 words, and gloss language-specific phenomena (tone sandhi, pitch accent) in one clause — reviewers outside your language's community must still follow the claim.

Titles: a quick calibration

  • Weak: "A Novel Deep Learning Framework for Improved Speech Processing" — no task, no mechanism, unsearchable.
  • Serviceable: "Prosody-Gated Chunking for Streaming ASR on Spontaneous Speech" — task, mechanism, condition, all in Archive-searchable vocabulary.
  • Community pattern: many memorable Interspeech titles name the system once ("Conformer: …", "SpecAugment: …") and then say plainly what it does; earn the name after the colon with a descriptive clause, not instead of one.

Output format

text
[One-pass check] task/method/corpus/metric/delta extractable from p.1? y/n
[Opening] title, abstract-number, index-terms verdicts
[Density audit] paragraphs convertible to one-liners or diffs
[Diction] bare numbers, undefined acronyms, unverifiable verbs found
[Compression plan] ordered cuts to reach 4 pages without claim loss
[Escalation] fits in 4pp / needs Long Paper / needs journal

Format facts (4 content pages + references page; Long Paper track parameters) follow the 2026 cycle as logged in resources/official-source-map.md (2026-07-08); the paper kit of the current cycle is the sole format authority.

© brycewang-stanford, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in INTERSPEECH-Skills/skills/interspeech-writing-style of brycewang-stanford/Awesome-Journal-Skills.

Open the folder on GitHubat commit 932eb23

Compare with similar skills

Interspeech Writing Style next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Interspeech Writing Style compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Interspeech Writing Style this skillbrycewang-stanford/Awesome-Journal-Skills1.2k—~1.6kAutomated safety check: PassMIT
Avoid AI Writingconorbronsdon/avoid-ai-writing4.9k3 repos~8.1kAutomated safety check: PassMIT
BrandOhh-889/skyroc79513 repos~733Automated safety check: PassMIT
Khazix WeChat Article WriterKKKKhazix/khazix-skills21k1 repos~2.9kAutomated safety check: PassMIT
Writing Guidelinesvercel-labs/agent-skills32k7 repos~309Automated safety check: PassNone
Unslop AI Writing Cleanuptheclaymethod/unslop518—~1.7kAutomated safety check: PassMIT

Similar skills

  • Avoid AI Writing

    conorbronsdon/avoid-ai-writing

    Audit and rewrite content to remove AI writing patterns ("AI-isms").

    4.9k GitHub starsUsed in 3 repos~8.1k tokens
    Writing & ContentAuto-check passed
  • Brand

    Ohh-889/skyroc

    Brand voice, visual identity, messaging frameworks, asset management, brand consistency.

    795 GitHub starsUsed in 13 repos~733 tokens
    Writing & ContentAuto-check passed
  • Khazix WeChat Article Writer

    KKKKhazix/khazix-skills

    Writes long-form WeChat official account articles in the personal style of the Khazix account, from briefs, links, PDFs or rough notes, with a topic quality check.

    21k GitHub starsUsed in 1 repo~2.9k tokens
    Writing & ContentAuto-check passed
  • Writing Guidelines

    vercel-labs/agent-skills

    Official

    Review docs/prose for Writing Guidelines compliance. An agent skill from vercel-labs/agent-skills.

    32k GitHub starsUsed in 7 repos~309 tokens
    Writing & ContentAuto-check passed
  • Unslop AI Writing Cleanup

    theclaymethod/unslop

    Removes AI writing tells from prose through an audit-first flow, routing to a two-pass rewrite, a report-only cleanup, voice teaching or mimicry depending on the sub-command used.

    518 GitHub stars~1.7k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed
  • UX Writing

    content-designer/ux-writing-skill

    Applies UX writing practice to interface copy such as buttons, errors, forms and onboarding, using four quality standards and accessibility guidance.

    224 GitHub starsUsed in 1 repo~3.8k tokens
    Writing & ContentAuto-check passed

More from brycewang-stanford/Awesome-Journal-Skills

All 2,387 skills in this repo
  • Aaag Data Analysis

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when running and reporting the analysis for an Annals of the American Association of Geographers manuscript — spatial statistics and modeling, remote-sensing accuracy, or…

    1.2k GitHub stars~1.3k tokensUpdated 14 days ago
    Auto-check passed
  • Aaag Literature Positioning

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when positioning an Annals of the American Association of Geographers manuscript in the literature — engaging geographic scholarship across the relevant area and the…

    1.2k GitHub stars~1.3k tokensUpdated 14 days ago
    Auto-check passed
  • Aaag Rebuttal

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when responding to an Annals of the American Association of Geographers decision letter (major/minor revision) — building a point-by-point response to the subject editor and…

    1.2k GitHub stars~1.4k tokensUpdated 14 days ago
    Auto-check passed
  • Aaag Research Design

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when defending the research design of an Annals of the American Association of Geographers manuscript — spatial/quantitative analysis and GIScience, remote-sensing and…

    1.2k GitHub stars~1.4k tokensUpdated 14 days ago
    Auto-check passed
  • Aaag Review Process

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when you need to understand how the Annals of the American Association of Geographers evaluates a manuscript — double-anonymous review routed through a subject editor by…

    1.2k GitHub stars~1.3k tokensUpdated 14 days ago
    Auto-check passed
  • Aaag Submission

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when running the final pre-submission preflight for the Annals of the American Association of Geographers via ScholarOne Manuscripts — area/article-type selection…

    1.2k GitHub stars~1.6k tokensUpdated 14 days ago
    Auto-check passed

Questions about Interspeech Writing Style

What does Interspeech Writing Style do?

A skill your agent uses when writing or compressing an INTERSPEECH paper into its 4 content pages — the abstract-and-index-terms opening, task-first framing for a mixed science/engineering…. Interspeech Writing Style is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when writing or compressing an INTERSPEECH paper into its 4 content pages — the abstract-and-index-terms opening, task-first framing for a mixed science/engineering readership, table and figure economy, protocol one-liners that preserve rigor under compression, and the cuts that shrink pages without shrinking claims.

When should I use Interspeech Writing Style?

Interspeech Writing Style fits situations like: compressing an INTERSPEECH paper into its 4 content pages — the abstract-and-index-terms opening; task-first framing for a mixed science/engineering readership; table and figure economy; protocol one-liners that preserve rigor under compression.

How do I install Interspeech Writing Style in Claude Code?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill interspeech-writing-style -a claude-code`. Or copy the skill folder (INTERSPEECH-Skills/skills/interspeech-writing-style in brycewang-stanford/Awesome-Journal-Skills) into .claude/skills/interspeech-writing-style in your project. Claude Code loads it when a task matches its description.

How do I install Interspeech Writing Style in Codex?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill interspeech-writing-style -a codex`. Or copy the skill folder (INTERSPEECH-Skills/skills/interspeech-writing-style in brycewang-stanford/Awesome-Journal-Skills) into .agents/skills/interspeech-writing-style in your project. Codex loads it when a task matches its description.

Can I use Interspeech Writing Style in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill interspeech-writing-style -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/interspeech-writing-style, .gemini/skills/interspeech-writing-style, .github/skills/interspeech-writing-style and .opencode/skills/interspeech-writing-style in your project.

What does Interspeech Writing Style need to run?

SKILL.md names no scripts, command-line tools or credentials: Interspeech Writing Style is instructions for the agent only.

Does Interspeech Writing Style access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Interspeech Writing Style safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Interspeech Writing Style use?

Interspeech Writing Style is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Interspeech Writing Style use?

About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Interspeech Writing Style?

Skills that share tags, products or a category with Interspeech Writing Style: Avoid AI Writing (conorbronsdon/avoid-ai-writing, 4.9k stars), Brand (Ohh-889/skyroc, 795 stars), Khazix WeChat Article Writer (KKKKhazix/khazix-skills, 21k stars) and Writing Guidelines (vercel-labs/agent-skills, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Interspeech Writing Style?

brycewang-stanford (a GitHub user) maintains it in brycewang-stanford/Awesome-Journal-Skills, which has 1,231 GitHub stars. The repository holds 2,387 skills in this directory. The repository was last updated on September 27, 2026.

Source: brycewang-stanford/Awesome-Journal-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.